A magnifying glass application system and method with a positioning structure

By designing a magnifying glass application system with a positioning structure, the image area is automatically recognized and enlarged, and the complex problem of manual verification and data entry in the prior art is solved, which improves the efficiency of image text recognition and reduces labor costs.

CN114821595BActive Publication Date: 2025-08-05OCEANX TECH SHENZHEN
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210530565.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-05-16
Publication Date
2025-08-05
Estimated Expiration
2042-05-16

AI Technical Summary

Technical Problem

The existing image text optical recognition software has complicated and complicated operation steps when manually verifying and entering data, resulting in large workload, low efficiency and high cost of manual operation.

Method used

Design a magnifying glass application system with a positioning structure, including a positioning magnifying glass module, through area coordinate input, conversion, pixel coordinate system establishment and dynamic optimization algorithms, automatically identify and enlarge the image area, and provide the optimized display area for users to view.

Benefits of technology

It reduces the repeated operations of users in the image text recognition process, improves work efficiency, reduces manual intervention and reduces labor costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114821595B_ABST
    Figure CN114821595B_ABST
Patent Text Reader

Abstract

The present invention discloses a magnifying glass application system and method with a positioning structure, comprising an image input module, an image processing module, a text recognition module, a region type judgment module, a region coordinate return module, a positioning magnifying glass module, a multi-line text type judgment submodule, a width priority algorithm submodule, a height priority algorithm submodule, an automatic cell splitting algorithm submodule, and an optimized display region output module. The method of use comprises the following steps: first, system initialization; second, image input; third, text recognition; and fourth, region magnification. The present invention adds a magnifying glass function to the image region text recognition system, and can automatically locate and magnify the metadata text region when the user views the region, so as to obtain the optimized display region for the user to view. The entire optimization process does not require manual intervention, and can effectively reduce the user's workload and improve work efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of document image text optical recognition, and in particular to a magnifying glass application system and method with a positioning structure. Background Art

[0002] Existing optical image and text recognition software mainly focuses on how to accurately identify text in images and subsequent workflow integration. However, optical recognition results cannot be absolutely accurate, and manual verification and data entry are inevitably required. However, existing recognition software has certain defects. When manually verifying and entering data, the operation steps are complicated and tedious, resulting in a large manual workload, low efficiency, and high labor costs. Summary of the Invention

[0003] The object of the present invention is to provide a magnifying glass application system and method with a positioning structure to solve the problems raised in the above background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a magnifying glass application system with a positioning structure, comprising a positioning magnifying glass module, the positioning magnifying glass module comprising an area coordinate input submodule, the area coordinate input submodule data is connected to a coordinate conversion submodule, the coordinate conversion submodule data is connected to a displayable range acquisition submodule, the displayable range acquisition submodule data is connected to a pixel coordinate system establishment submodule, the pixel coordinate system establishment submodule data is connected to a dynamic optimization algorithm submodule, the dynamic optimization algorithm submodule data is connected to an area text type judgment submodule, the area text type judgment submodule data is connected to a multi-line text type judgment submodule and a width-first algorithm submodule, the multi-line text type judgment submodule data is connected to a height-first algorithm submodule and an automatic cell splitting algorithm submodule.

[0005] Preferably, the output results of the area type judgment module are of two types, one is a search area, and the other is a common area.

[0006] Preferably, the output results of the regional text type judgment submodule are of two types, one is multi-line text, and the other is single-line text.

[0007] Preferably, the output results of the multi-line text type judgment submodule are of two types, one is ordinary multi-line text, and the other is table type multi-line text.

[0008] Preferably, the output end data of the positioning magnifying glass module is connected to the optimized display area output module, and the width-first algorithm submodule, the height-first algorithm submodule and the automatic cell splitting algorithm submodule are all data connected to the optimized display area output module.

[0009] Preferably, the input end data of the positioning magnifying glass module is connected to the area coordinate return module, the input end data of the area coordinate return module is connected to the area type judgment module, the input end data of the area type judgment module is connected to the text recognition module, the input end data of the text recognition module is connected to the image processing module, and the input end data of the image processing module is connected to the image input module.

[0010] A method for using a magnifying glass application system with a positioning structure, comprising the steps of: first, system initialization; second, image input; third, text recognition; and fourth, area magnification.

[0011] In step 1 above, the user sets up the image matching template in the system, including the text area to be recognized and various attribute settings, and also sets the scanning parameters, including DPI, etc.

[0012] In the above step 2, the user uses a scanning terminal to scan an image, and the image input module transmits the image to the image processing module;

[0013] In step 3 above, the image processing module normalizes the image to the set DPI, and the text recognition module recognizes the text in the specified area;

[0014] In the above step 4, the user enters the information verification and metadata entry interface. When the user views the metadata text area, the area type judgment module determines the area type. The area coordinate return module returns the area coordinates based on twips to the positioning magnifier module based on the judgment result. The positioning magnifier module processes the area coordinates and outputs the optimized display area through the optimized display area output module. The area will be dynamically enlarged and placed in the visible area for the user to view.

[0015] Preferably, in step four, the specific method for the positioning magnifying glass module to process the regional coordinates is: the regional coordinates based on twips are transmitted by the regional coordinate input submodule to the coordinate conversion submodule, the coordinate conversion submodule converts the twip coordinates into pixel coordinates, the displayable range acquisition submodule obtains the image displayable range based on this, the pixel coordinate system establishment submodule establishes a pixel coordinate system on the image within the display range, the dynamic optimization algorithm submodule optimizes the pixel display area, and the optimized display area output module outputs the result.

[0016] Preferably, the specific optimization method of the dynamic optimization algorithm submodule is: the regional text type is judged by the regional text type judgment submodule, when the judgment result is a single line of text, the width priority algorithm submodule is executed, when the judgment result is multiple lines of text, the multiple lines of text type judgment submodule is used to judge it again, if the judgment result is ordinary type, the height priority algorithm submodule is executed, if the judgment result is a table type, the automatic cell splitting algorithm submodule is executed, after algorithm processing, the optimized display area can be output by the optimized display area output module.

[0017] Compared with the existing technology, the present invention has the following advantages: the present invention adds a magnifying glass function to the image area text recognition system, which can automatically locate and magnify the metadata text area when the user views it, and obtain the optimized display area for the user to view. The entire optimization process does not require manual intervention, which can effectively reduce the user's workload and improve work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a system block diagram of the present invention;

[0019] Figure 2 is a system flow chart of the present invention;

[0020] Figure 3 is a flow chart of the method of the present invention;

[0021] Figure 4 This is a diagram of the system software image matching template setting interface of the present invention;

[0022] Figure 5 This is a diagram of the system software parameter setting interface of the present invention;

[0023] Figure 6 This is the interface diagram for verifying system software information and entering metadata of the present invention;

[0024] In the figure: 1. Image input module; 2. Image processing module; 3. Text recognition module; 4. Area type judgment module; 5. Area coordinate return module; 6. Positioning magnifying glass module; 60. Area coordinate input submodule; 61. Coordinate conversion submodule; 62. Displayable range acquisition submodule; 63. Pixel coordinate system establishment submodule; 64. Dynamic optimization algorithm submodule; 65. Area text type judgment submodule; 66. Multi-line text type judgment submodule; 67. Width-first algorithm submodule; 68. Height-first algorithm submodule; 69. Automatic cell splitting algorithm submodule; 7. Optimized display area output module. DETAILED DESCRIPTION

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0026] See also Figure 1 An embodiment of the present invention provides: a magnifying glass application system with a positioning structure, including a positioning magnifying glass module 6, the positioning magnifying glass module 6 includes a regional coordinate input submodule 60, the regional coordinate input submodule 60 is data-connected to a coordinate conversion submodule 61, the coordinate conversion submodule 61 is data-connected to a displayable range acquisition submodule 62, the displayable range acquisition submodule 62 is data-connected to a pixel coordinate system establishment submodule 63, the pixel coordinate system establishment submodule 63 is data-connected to a dynamic optimization algorithm submodule 64, the dynamic optimization algorithm submodule 64 is data-connected to a regional text type judgment submodule 65, the regional text type judgment submodule 65 is data-connected to a multi-line text type judgment submodule 66 and a width-first algorithm submodule 67, the multi-line text type judgment submodule 66 is data-connected to a height-first algorithm submodule 68 and an automatic cell splitting algorithm submodule 69; there are two output results of the regional type judgment module 4, One is the search type area, and the other is the ordinary area; there are two types of output results of the regional text type judgment submodule 65, one is multi-line text, and the other is single-line text; there are two types of output results of the multi-line text type judgment submodule 66, one is ordinary multi-line text, and the other is table type multi-line text; the output end data of the positioning magnifying glass module 6 is connected to the optimized display area output module 7, and the width priority algorithm submodule 67, the height priority algorithm submodule 68 and the automatic cell splitting algorithm submodule 69 all establish data connections with the optimized display area output module 7; the input end data of the positioning magnifying glass module 6 is connected to the regional coordinate return module 5, the input end data of the regional coordinate return module 5 is connected to the regional type judgment module 4, the input end data of the regional type judgment module 4 is connected to the text recognition module 3, the input end data of the text recognition module 3 is connected to the image processing module 2, and the input end data of the image processing module 2 is connected to the image input module 1.

[0027] See also Figure 2-6 The present invention provides an embodiment: a method for using a magnifying glass application system with a positioning structure, comprising the steps of: first, system initialization; second, image input; third, text recognition; and fourth, area magnification.

[0028] In step 1 above, the user sets up the image matching template in the system, including the text area to be recognized and various attribute settings, and also sets the scanning parameters, including DPI, etc.

[0029] In the above step 2, the user uses a scanning terminal to scan an image, and the image input module 1 transmits the image to the image processing module 2;

[0030] In the above step 3, the image processing module 2 normalizes the image to the set DPI, and the text recognition module 3 recognizes the text in the specified area;

[0031] In the above step 4, the user enters the information verification and metadata entry interface. When the user views the metadata text area, the area type judgment module 4 judges the area type, and the area coordinate return module 5 returns the area coordinates based on twips to the positioning magnifying glass module 6 according to the judgment result. The positioning magnifying glass module 6 processes the area coordinates and outputs the optimized display area through the optimized display area output module 7. The area will be dynamically enlarged and placed in the visual area for the user to view. The specific method for the positioning magnifying glass module 6 to process the area coordinates is as follows: the area coordinates based on twips are transmitted from the area coordinate input submodule 60 to the coordinate conversion submodule 61. The coordinate conversion submodule 61 converts the twip coordinates into pixel coordinates, and the display range is obtained. The acquisition submodule 62 obtains the displayable range of the image based on this, the pixel coordinate system establishment submodule 63 establishes a pixel coordinate system on the image within the display range, the dynamic optimization algorithm submodule 64 optimizes the pixel display area, and the regional text type judgment submodule 65 judges the regional text type. When the judgment result is a single line of text, the width priority algorithm submodule 67 is executed. When the judgment result is multiple lines of text, the multiple lines of text type judgment submodule 66 judges it again. If the judgment result is ordinary type, the height priority algorithm submodule 68 is executed. If the judgment result is a table type, the automatic cell splitting algorithm submodule 69 is executed. After algorithm processing, the optimized display area can be output by the optimized display area output module 7.

[0032] Based on the above, the advantage of the present invention is that when the present invention is used for image and text recognition, the image input module 1 enters the image data into the system, and after pre-processing by the image processing module 2, the text recognition module 3 recognizes it. When the user views a certain area, the area type judgment module 4 judges the area, and the area coordinate return module 5 returns the area coordinates based on twips to the positioning magnifying glass module 6 according to the judgment result. The positioning magnifying glass module 6 optimizes the area coordinates based on twips and can directly obtain the optimized display area. The entire optimization process does not require human intervention, which greatly reduces the user's repetitive and inefficient operations, saves working time, and significantly improves the user's work efficiency.

[0033] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A magnifying glass application system with a positioning structure, comprising a positioning magnifying glass module (6), characterized in that: The positioning magnifying glass module (6) includes a regional coordinate input submodule (60), the regional coordinate input submodule (60) is data-connected to a coordinate conversion submodule (61), the coordinate conversion submodule (61) is data-connected to a displayable range acquisition submodule (62), the displayable range acquisition submodule (62) is data-connected to a pixel coordinate system establishment submodule (63), the pixel coordinate system establishment submodule (63) is data-connected to a dynamic optimization algorithm submodule (64), the dynamic optimization algorithm submodule (64) is data-connected to a regional text type judgment submodule (65), the regional text type judgment submodule (65) is data-connected to a multi-line text type judgment submodule (66) and a width-first algorithm submodule (67), the multi-line text type judgment submodule (66) is data-connected to a height-first algorithm submodule (68) and an automatic cell splitting algorithm submodule (69), the output end of the positioning magnifying glass module (6) is data-connected to an optimized display area output module (7), and the width-first algorithm The submodule (67), the height priority algorithm submodule (68) and the automatic cell splitting algorithm submodule (69) all establish data connections with the optimized display area output module (7). The input end data of the positioning magnifying glass module (6) is connected to the area coordinate return module (5), the input end data of the area coordinate return module (5) is connected to the area type judgment module (4), the input end data of the area type judgment module (4) is connected to the text recognition module (3), the input end data of the text recognition module (3) is connected to the image processing module (2), and the input end data of the image processing module (2) is connected to the image input module (1). The output results of the area type judgment module (4) are of two types, one is a search type area and the other is an ordinary area. The output results of the area text type judgment submodule (65) are of two types, one is multi-line text and the other is single-line text. The output results of the multi-line text type judgment submodule (66) are of two types, one is ordinary multi-line text and the other is table type multi-line text.

2. A method for using the magnifying glass application system with a positioning structure according to claim 1, comprising step 1: system initialization; step 2: image input; step 3: text recognition; and step 4: area magnification; characterized in that: In step 1 above, the user sets up the image matching template in the system, including the text area to be recognized and various attribute settings, and also sets the scanning parameters, including DPI; In the above step 2, the user uses a scanning terminal to scan an image, and the image input module (1) transmits the image to the image processing module (2); In the above step 3, the image processing module (2) normalizes the image to the set DPI, and the text recognition module (3) recognizes the text in the specified area; In the above step 4, the user enters the information verification and metadata input interface. When the user views the metadata text area, the area type judgment module (4) judges the area type. The area coordinate return module (5) returns the area coordinates based on twips to the positioning magnifier module (6) according to the judgment result. The positioning magnifier module (6) processes the area coordinates and outputs the optimized display area through the optimized display area output module (7). The optimized display area will be dynamically enlarged and placed in the visual area for the user to view.

3. The method for using the magnifying glass application system with a positioning structure according to claim 2, characterized in that: In the step 4, the specific method for the positioning magnifying glass module (6) to process the regional coordinates is as follows: the regional coordinates based on twips are transmitted by the regional coordinate input submodule (60) to the coordinate conversion submodule (61), the coordinate conversion submodule (61) converts the twips coordinates into pixel coordinates, the displayable range acquisition submodule (62) obtains the image displayable range based on the twips, the pixel coordinate system establishment submodule (63) establishes a pixel coordinate system on the image within the display range, the dynamic optimization algorithm submodule (64) optimizes the pixel display area, and the optimized display area output module (7) outputs the result.

4. The method for using the magnifying glass application system with a positioning structure according to claim 2, characterized in that: The specific optimization method of the dynamic optimization algorithm submodule (64) is as follows: the regional text type is judged by the regional text type judgment submodule (65); when the judgment result is a single-line text, the width-first algorithm submodule (67) is executed; when the judgment result is a multi-line text, the multi-line text type judgment submodule (66) is used to judge it again; if the judgment result is a normal type, the height-first algorithm submodule (68) is executed; if the judgment result is a table type, the automatic cell splitting algorithm submodule (69) is executed; after the algorithm processing, the optimized display area can be output by the optimized display area output module (7).

Citation Information

Patent Citations

  • Character positioning frame determination method and device, medium and electronic equipment

    CN112183531A

  • Image character recognition method and device thereof

    CN112418238A